← Back to CVE List
CVE-2026-82447NVD
Vulnerability Summary
Skyvern before 1.0.45 contains a sandbox escape vulnerability in TextPromptBlock that renders prompts twice, first through a sandboxed Jinja environment and then through an unsandboxed environment. Attackers can inject malicious Jinja template syntax through workflow parameters or upstream block output to execute arbitrary code with server process privileges.
CVSS v3.1 Base Metrics
Attack VectorNetwork
Attack ComplexityLow
Privileges RequiredLow
User InteractionNone
ScopeUnchanged
ConfidentialityHigh
IntegrityHigh
AvailabilityHigh
External References
- https://github.com/Skyvern-AI/skyvern/commit/d723de621d5b3a340f3cc4d5b46bfe40a9a3124e
- https://github.com/Skyvern-AI/skyvern
- https://github.com/Skyvern-AI/skyvern/blob/v1.0.44/skyvern/forge/sdk/workflow/models/block.py
- https://github.com/Skyvern-AI/skyvern/blob/v1.0.44/skyvern/forge/sdk/prompting.py
- https://www.vulncheck.com/advisories/skyvern-before-1.0.45-sandbox-escape-via-textpromptblock